← authors · overview

• Practical Black-Box Attacks against Machine Learning
  2016 · 101 citations
• The Limitations of Deep Learning in Adversarial Settings
  2015 · 72 citations
• Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting
  2017 · 11 citations
• Is Private Learning Possible with Instance Encoding?
  2020 · 11 citations
• Adversarial Binaries for Authorship Identification
  2018 · 10 citations
• Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
  2015 · 8 citations
• Towards Understanding Limitations of Pixel Discretization Against Adversarial Attacks
  2018 · 4 citations
• How Not to Detect Prompt Injections with an LLM
  2025 · 3 citations
• Systems Security Foundations for Agentic Computing
  2025
• GRAPHITE: Generating Automatic Physical Examples for Machine-Learning Attacks on Computer Vision Systems
  2020
• PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
  2024